© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149187
    Prev
    Next
    INDEX
    Explanations

    rolesubjectfunctionDeleteReserved

    np_acts-logits-general · gemini-2.5-flash-lite

    productivity and leisure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ai
    0.64
    ip
    0.54
    GA
    0.52
    0
    0.50
     ;
    0.49
    GE
    0.49
    og
    0.49
    oo
    0.47
     GA
    0.47
     hear
    0.47
    POSITIVE LOGITS
    আনন্দ
    0.63
    躹
    0.59
     годы
    0.53
    獷
    0.53
     আনন্দ
    0.52
     भावनात्मक
    0.51
     Лю
    0.51
     বিদ্ব
    0.51
    陣
    0.51
     उमेश
    0.50
    Activations Density 0.000%

    No Known Activations